Cif-based Collaborative Decoding For End-to-end Contextual Speech Recognition

Abstract

End-to-end (E2E) models have achieved promising results on multiple speech recognition benchmarks, and shown the potential to become the mainstream. However, the unified structure and the E2E training hamper injecting contextual information into them for contextual biasing. Though contextual LAS (CLAS) gives an excellent all-neural solution, the degree of biasing to given context information is not explicitly controllable. In this paper, we focus on incorporating context information into the continuous integrate-and-fire (CIF) based model that supports contextual biasing in a more controllable fashion. Specifically, an extra context processing network is introduced to extract contextual embeddings, integrate acoustically relevant context information and decode the contextual output distribution, thus forming a collaborative decoding with the decoder of the CIF-based model. Evaluated on the named entity rich evaluation sets of HKUST/AISHELL-2, our method brings relative character error

Stats

• citations19
• S2 citations—
• github stars0
• HF likes0
• heat score9.76
• arxiv keyhan2020cif

Related papers

• Deep Context: End-to-end Contextual Speech Recognition (2018)15.57
• End-to-end Contextual Speech Recognition Using Class Language Models And A Token Passing Decoder (2018)11.08
• End-to-end Contextual Asr Based On Posterior Distribution Adaptation For Hybrid Ctc/attention System (2022)0.00
• Efficient Long-form Speech Recognition For General Speech In-context Learning (2024)0.00
• Boundary And Context Aware Training For Cif-based Non-autoregressive End-to-end ASR (2021)7.81
• Contextualized Streaming End-to-end Speech Recognition With Trie-based Deep Biasing And Shallow Fusion (2021)13.44
• Contextualized End-to-end Automatic Speech Recognition With Intermediate Biasing Loss (2024)5.84
• Improving Neural Biasing For Contextual Speech Recognition By Early Context Injection And Text Perturbation (2024)8.09